Provable Multi-task Reinforcement Learning: A Representation Learning Framework With Low Rank Rewards

Abstract

Multi-task representation learning (MTRL) is an approach that learns shared latent representations across related tasks, facilitating collaborative learning that improves the overall learning efficiency. This paper studies MTRL for multi-task reinforcement learning (RL), where multiple tasks have the same state-action space and transition probabilities, but different rewards. We consider T linear Markov Decision Processes (MDPs) where the reward functions and transition dynamics admit linear feature embeddings of dimension d. The relatedness among the tasks is captured by a low-rank structure on the reward matrices. Learning shared representations across multiple RL tasks is challenging due to the complex and policy-dependent nature of data that leads to a temporal progression of error. Our approach adopts a reward-free reinforcement learning framework to first learn a data-collection policy. This policy then informs an exploration strategy for estimating the unknown reward matrices. I

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyguo2026provable

Related papers

• Provable Benefit Of Multitask Representation Learning In Reinforcement Learning (2022)0.00
• A Decentralized Policy Gradient Approach To Multi-task Reinforcement Learning (2020)0.00
• Provably Efficient Multi-task Reinforcement Learning With Model Transfer (2021)0.00
• Towards Understanding The Benefit Of Multitask Representation Learning In Decision Process (2025)0.00
• Accelerating Multi-task Temporal Difference Learning Under Low-rank Representation (2025)0.00
• Multi-user Reinforcement Learning With Low Rank Rewards (2022)0.00
• Sample Efficient Myopic Exploration Through Multitask Reinforcement Learning With Diverse Tasks (2024)0.00
• Provable Benefits Of Multi-task RL Under Non-markovian Decision Making Processes (2023)0.00